// SCAN REPORT

Cortex Memory

5 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 12 Jun 2026

1 can modify or destroy data

4 read-only

5 tools total

Community server · catalogue entry verified 12/06/2026

How to control Cortex Memory ↓

TOOL MAP

What Cortex Memory exposes to your agents

Read (4) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Cortex Memory tools

Write · Medium cortex_save_memory This tool creates and stores new data (memories, decisions, insights) in the cortex system, making it a Write operation.

1 of Cortex Memory's 5 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Cortex Memory

PolicyLayer is an MCP gateway — it sits between your AI agents and Cortex Memory, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "cortex_save_memory": {
    "limits": [
      {
        "counter": "cortex_save_memory_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "cortex_get_context": {
    "limits": [
      {
        "counter": "cortex_get_context_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Cortex Memory — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON CORTEX MEMORY →

Free to start. No card required.

FULL CATALOGUE

All 5 Cortex Memory tools

WRITE 1 tools

Write cortex_save_memory Saves a new memory, decision, or insight from the current session.

READ 4 tools

Read cortex_get_context Returns the current working memory (Layer 1) as formatted text. Read cortex_get_decisions Returns all architectural decisions (ADRs) recorded for this project. Read cortex_search Searches episodic and semantic memory for matching episodes and decisions. Read cortex_status Returns memory health status including health score, entry counts, and warnings.

FAQ

Questions about Cortex Memory

How do I prevent bulk modifications through Cortex Memory? +

The Cortex Memory server has 1 write tools including cortex_save_memory. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Cortex Memory.

How many tools does the Cortex Memory MCP server expose? +

5 tools across 2 categories: Read, Write. 4 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on Cortex Memory? +

Register the Cortex Memory MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Cortex Memory tool call.

Deterministic rules across all 5 Cortex Memory tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CORTEX MEMORY →

Free to start. No card required.

5 Cortex Memory tools catalogued and risk-classified — across an index of 43,000+ MCP servers.